This patch makes fold-const.c operate directly on the VECTOR_CST
encoding when folding an operation that has a single VECTOR_CST input.
Tested on aarch64-linux-gnu, x86_64-linux-gnu and powerpc64le-linux-gnu.
Also spot-checked on sparc64-linux-gnu. OK to install?
Thanks,
Richard
2017-12-06 Richard Sandiford <richard.sandif...@linaro.org>
gcc/
* fold-const.c (fold_negate_expr_1): Use tree_vector_builder and
new_unary_operation, operating only on the encoded elements.
(const_unop): Likewise.
(exact_inverse): Likewise.
(distributes_over_addition_p): New function.
(const_binop): Use tree_vector_builder and new_unary_operation
for combinations of VECTOR_CST and INTEGER_CST. Operate only
on the encoded elements unless the encoding is strided and the
operation does not distribute over addition.
(fold_convert_const): Use tree_vector_builder and
new_unary_operation. Operate only on the encoded elements
for truncating integer conversions, or for non-stepped encodings.
Index: gcc/fold-const.c
===================================================================
--- gcc/fold-const.c 2017-12-06 14:48:52.887162217 +0000
+++ gcc/fold-const.c 2017-12-06 14:48:56.997993407 +0000
@@ -566,10 +566,10 @@ fold_negate_expr_1 (location_t loc, tree
case VECTOR_CST:
{
- int count = VECTOR_CST_NELTS (t), i;
-
- auto_vec<tree, 32> elts (count);
- for (i = 0; i < count; i++)
+ tree_vector_builder elts;
+ elts.new_unary_operation (type, t, true);
+ unsigned int count = elts.encoded_nelts ();
+ for (unsigned int i = 0; i < count; ++i)
{
tree elt = fold_negate_expr (loc, VECTOR_CST_ELT (t, i));
if (elt == NULL_TREE)
@@ -577,7 +577,7 @@ fold_negate_expr_1 (location_t loc, tree
elts.quick_push (elt);
}
- return build_vector (type, elts);
+ return elts.build ();
}
case COMPLEX_EXPR:
@@ -1121,6 +1121,27 @@ int_const_binop (enum tree_code code, co
return int_const_binop_1 (code, arg1, arg2, 1);
}
+/* Return true if binary operation OP distributes over addition in operand
+ OPNO, with the other operand being held constant. OPNO counts from 1. */
+
+static bool
+distributes_over_addition_p (tree_code op, int opno)
+{
+ switch (op)
+ {
+ case PLUS_EXPR:
+ case MINUS_EXPR:
+ case MULT_EXPR:
+ return true;
+
+ case LSHIFT_EXPR:
+ return opno == 1;
+
+ default:
+ return false;
+ }
+}
+
/* Combine two constants ARG1 and ARG2 under operation CODE to produce a new
constant. We assume ARG1 and ARG2 have the same data type, or at least
are the same kind of constant and the same machine mode. Return zero if
@@ -1442,10 +1463,12 @@ const_binop (enum tree_code code, tree a
&& TREE_CODE (arg2) == INTEGER_CST)
{
tree type = TREE_TYPE (arg1);
- int count = VECTOR_CST_NELTS (arg1), i;
-
- auto_vec<tree, 32> elts (count);
- for (i = 0; i < count; i++)
+ bool step_ok_p = distributes_over_addition_p (code, 1);
+ tree_vector_builder elts;
+ if (!elts.new_unary_operation (type, arg1, step_ok_p))
+ return NULL_TREE;
+ unsigned int count = elts.encoded_nelts ();
+ for (unsigned int i = 0; i < count; ++i)
{
tree elem1 = VECTOR_CST_ELT (arg1, i);
@@ -1458,7 +1481,7 @@ const_binop (enum tree_code code, tree a
elts.quick_push (elt);
}
- return build_vector (type, elts);
+ return elts.build ();
}
return NULL_TREE;
}
@@ -1649,10 +1672,12 @@ const_unop (enum tree_code code, tree ty
else if (TREE_CODE (arg0) == VECTOR_CST)
{
tree elem;
- unsigned count = VECTOR_CST_NELTS (arg0), i;
- auto_vec<tree, 32> elements (count);
- for (i = 0; i < count; i++)
+ /* This can cope with stepped encodings because ~x == -1 - x. */
+ tree_vector_builder elements;
+ elements.new_unary_operation (type, arg0, true);
+ unsigned int i, count = elements.encoded_nelts ();
+ for (i = 0; i < count; ++i)
{
elem = VECTOR_CST_ELT (arg0, i);
elem = const_unop (BIT_NOT_EXPR, TREE_TYPE (type), elem);
@@ -1661,7 +1686,7 @@ const_unop (enum tree_code code, tree ty
elements.quick_push (elem);
}
if (i == count)
- return build_vector (type, elements);
+ return elements.build ();
}
break;
@@ -2135,10 +2160,19 @@ fold_convert_const (enum tree_code code,
if (TREE_CODE (arg1) == VECTOR_CST
&& TYPE_VECTOR_SUBPARTS (type) == VECTOR_CST_NELTS (arg1))
{
- int len = VECTOR_CST_NELTS (arg1);
tree elttype = TREE_TYPE (type);
- auto_vec<tree, 32> v (len);
- for (int i = 0; i < len; ++i)
+ tree arg1_elttype = TREE_TYPE (TREE_TYPE (arg1));
+ /* We can't handle steps directly when extending, since the
+ values need to wrap at the original precision first. */
+ bool step_ok_p
+ = (INTEGRAL_TYPE_P (elttype)
+ && INTEGRAL_TYPE_P (arg1_elttype)
+ && TYPE_PRECISION (elttype) <= TYPE_PRECISION (arg1_elttype));
+ tree_vector_builder v;
+ if (!v.new_unary_operation (type, arg1, step_ok_p))
+ return NULL_TREE;
+ unsigned int len = v.encoded_nelts ();
+ for (unsigned int i = 0; i < len; ++i)
{
tree elt = VECTOR_CST_ELT (arg1, i);
tree cvt = fold_convert_const (code, elttype, elt);
@@ -2146,7 +2180,7 @@ fold_convert_const (enum tree_code code,
return NULL_TREE;
v.quick_push (cvt);
}
- return build_vector (type, v);
+ return v.build ();
}
}
return NULL_TREE;
@@ -8832,7 +8866,6 @@ exact_inverse (tree type, tree cst)
REAL_VALUE_TYPE r;
tree unit_type;
machine_mode mode;
- unsigned vec_nelts, i;
switch (TREE_CODE (cst))
{
@@ -8846,12 +8879,14 @@ exact_inverse (tree type, tree cst)
case VECTOR_CST:
{
- vec_nelts = VECTOR_CST_NELTS (cst);
unit_type = TREE_TYPE (type);
mode = TYPE_MODE (unit_type);
- auto_vec<tree, 32> elts (vec_nelts);
- for (i = 0; i < vec_nelts; i++)
+ tree_vector_builder elts;
+ if (!elts.new_unary_operation (type, cst, false))
+ return NULL_TREE;
+ unsigned int count = elts.encoded_nelts ();
+ for (unsigned int i = 0; i < count; ++i)
{
r = TREE_REAL_CST (VECTOR_CST_ELT (cst, i));
if (!exact_real_inverse (mode, &r))
@@ -8859,7 +8894,7 @@ exact_inverse (tree type, tree cst)
elts.quick_push (build_real (unit_type, r));
}
- return build_vector (type, elts);
+ return elts.build ();
}
default:
